sq_df = read_csv('squirrel_tidy.csv') %>% 
  janitor::clean_names()

Longitudinal Model

\(H_0:\) Every parameter of predictors in our regression model is equal to zero.

\(H_1:\) Not every parameter of predictors in our regression model is equal to zero.

long_model_final = lm(long ~ shift + age + activity + reaction + sounds, data = sq_df)
anova(long_model_final) %>% 
  knitr::kable()
Df Sum Sq Mean Sq F value Pr(>F)
shift 1 0.0002502 0.0002502 4.245234 0.0394462
age 1 0.0004462 0.0004462 7.569035 0.0059734
activity 1 0.0003009 0.0003009 5.103838 0.0239441
reaction 1 0.0004229 0.0004229 7.175147 0.0074321
sounds 1 0.0011391 0.0011391 19.324337 0.0000114
Residuals 3017 0.1778414 0.0000589 NA NA

We use anova test to make sure the predictors of our final Longitudinal regression fit are significant. Based on the results, the p-values of all five predictors (shift, age, activity, reaction and sounds) are smaller than 0.05 so we reject the null hypothesis and conclude that every predictor in our final longitudinal model is significant.

Latitudinal Model

\(H_0:\) Every parameter of predictors in our regression model is equal to zero.

\(H_1:\) Not every parameter of predictors in our regression model is equal to zero.

lat_model_final = lm(lat ~ primary_fur_color + reaction + sounds, data = sq_df)
anova(lat_model_final) %>% 
    knitr::kable()
Df Sum Sq Mean Sq F value Pr(>F)
primary_fur_color 1 0.0012564 0.0012564 12.03392 0.0005297
reaction 1 0.0011339 0.0011339 10.86081 0.0009936
sounds 1 0.0021015 0.0021015 20.12823 0.0000075
Residuals 3019 0.3151947 0.0001044 NA NA

We use the same way (anova test) to make sure the predictors of our final Latitudinal regression fit are significant. Based on the results, the p-values of all three predictors (primary fur color, reaction and sounds) are smaller than 0.05 so we reject the null hypothesis and conclude that every predictor in our final latitudinal model is significant.